VeriSpace: 面向视觉-语言-动作模型的空间基础动作验证
VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models
AI总结:
提出VeriSpace,一种3D感知的动作验证器,通过双路径3D注入场景编码和空间基础动作推理,在测试时选择候选动作,提升VLA模型的可靠性。
摘要:
视觉-语言-动作(VLA)模型在机器人操作中展现出强大潜力,但其测试时的可靠性仍受限于一次性动作预测,即使微小的动作误差也可能导致抓取失败、碰撞或任务进展错误。一种自然的替代方案是为VLA系统配备测试时验证,允许在执行前提出并评估多个候选动作。然而,可靠的动作验证具有挑战性,因为它不仅需要区分候选动作之间的细微几何差异,还需要评估动作是否朝着任务目标有意义地推进。我们提出VeriSpace,一种用于VLA系统测试时动作选择的3D感知动作验证器。VeriSpace通过两个关键组件评估候选动作:双路径3D注入场景编码,构建同时保留视觉语义和显式3D几何的场景表示;以及空间基础动作推理,通过推理任务相关的空间关系、几何有效性和预期的目标进展来评估每个动作。这些组件共同实现了对细微但结果关键的候选动作更可靠的区分,同时与现有VLA策略完全兼容。在公共基准和真实机器人操作任务上的实验表明,VeriSpace在分布内和分布外设置中均持续提高了底层VLA策略和先前基于验证的方法的决策可靠性,带来了显著的性能提升。
英文摘要:
Vision-language-action (VLA) models have shown strong promise for robotic manipulation, but their reliability at test time remains limited by one-shot action prediction, where even small action errors can cause grasp failure, collision, or incorrect task progression. A natural alternative is to equip VLA systems with test-time verification, allowing multiple candidate actions to be proposed and evaluated before execution. However, reliable action verification is challenging because it requires not only distinguishing subtle geometric differences between candidate actions, but also assessing whether an action makes meaningful progress toward the task goal. We present VeriSpace, a 3D-aware action verifier for test-time action selection in VLA systems. VeriSpace evaluates candidate actions through two key components: Dual-Path 3D-Injected Scene Encoding, which constructs a scene representation that jointly preserves visual semantics and explicit 3D geometry, and Spatially-Grounded Action Reasoning, which evaluates each action by reasoning over task-relevant spatial relations, geometric validity, and expected goal progress. Together, these components enable more reliable discrimination between subtle yet outcome-critical action candidates while remaining fully compatible with existing VLA policies. Experiments on public benchmarks and real-world robotic manipulation tasks show that VeriSpace consistently improves decision reliability over both underlying VLA policies and prior verification-based methods, yielding substantial gains in both in-distribution and out-of-distribution settings.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。